© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 56001
    Prev
    Next
    INDEX
    Explanations

    code documentation comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (strict
    -0.10
     retention
    -0.09
     lille
    -0.09
    aston
    -0.09
     dik
    -0.09
     Aid
    -0.09
    æºIJ
    -0.09
    iken
    -0.09
     Instit
    -0.09
    çī
    -0.09
    POSITIVE LOGITS
     Roland
    0.09
    asl
    0.08
    ish
    0.08
    ifa
    0.08
    beck
    0.07
     Zub
    0.07
    agements
    0.07
     enumer
    0.07
    }};↵
    0.07
     Mum
    0.07
    Activations Density 0.007%

    No Known Activations